Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1554 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.0735. Min Range: -1.0735

Max Act: 1.0735. Min Act: -0.0003

Data Index: 1032118 (C4 (Web Text))

Max Activating Token Index: 454

Text #1

Max Range: 1.0735. Min Range: -1.0735

Max Act: 0.6187. Min Act: -0.0003

Data Index: 1166287 (C4 (Web Text))

Max Activating Token Index: 402

Text #2

Max Range: 1.0735. Min Range: -1.0735

Max Act: 0.9165. Min Act: -0.0003

Data Index: 231023 (C4 (Web Text))

Max Activating Token Index: 940

Text #3

Max Range: 1.0735. Min Range: -1.0735

Max Act: 0.6755. Min Act: -0.0003

Data Index: 10165 (C4 (Web Text))

Max Activating Token Index: 495

Text #4

Max Range: 1.0735. Min Range: -1.0735

Max Act: 0.7187. Min Act: -0.0003

Data Index: 598052 (C4 (Web Text))

Max Activating Token Index: 382

Text #5

Max Range: 1.0735. Min Range: -1.0735

Max Act: 0.7539. Min Act: -0.0003

Data Index: 437980 (C4 (Web Text))

Max Activating Token Index: 480

Text #6

Max Range: 1.0735. Min Range: -1.0735

Max Act: 0.4346. Min Act: -0.0003

Data Index: 16129 (C4 (Web Text))

Max Activating Token Index: 337

Text #7

Max Range: 1.0735. Min Range: -1.0735

Max Act: 0.4115. Min Act: -0.0003

Data Index: 266085 (C4 (Web Text))

Max Activating Token Index: 303

Text #8

Max Range: 1.0735. Min Range: -1.0735

Max Act: 0.6401. Min Act: -0.0003

Data Index: 257394 (C4 (Web Text))

Max Activating Token Index: 186

Text #9

Max Range: 1.0735. Min Range: -1.0735

Max Act: 0.6968. Min Act: -0.0003

Data Index: 1000127 (C4 (Web Text))

Max Activating Token Index: 433

Text #10

Max Range: 1.0735. Min Range: -1.0735

Max Act: 0.5839. Min Act: -0.0003

Data Index: 145751 (C4 (Web Text))

Max Activating Token Index: 11

Text #11

Max Range: 1.0735. Min Range: -1.0735

Max Act: 0.7241. Min Act: -0.0003

Data Index: 833514 (C4 (Web Text))

Max Activating Token Index: 163

Text #12

Max Range: 1.0735. Min Range: -1.0735

Max Act: 0.8125. Min Act: -0.0003

Data Index: 1040977 (C4 (Web Text))

Max Activating Token Index: 11

Text #13

Max Range: 1.0735. Min Range: -1.0735

Max Act: 0.4666. Min Act: -0.0003

Data Index: 137083 (C4 (Web Text))

Max Activating Token Index: 913

Text #14

Max Range: 1.0735. Min Range: -1.0735

Max Act: 0.3032. Min Act: -0.0003

Data Index: 703320 (C4 (Web Text))

Max Activating Token Index: 592

Text #15

Max Range: 1.0735. Min Range: -1.0735

Max Act: 0.4996. Min Act: -0.0003

Data Index: 902297 (C4 (Web Text))

Max Activating Token Index: 277

Text #16

Max Range: 1.0735. Min Range: -1.0735

Max Act: 0.6316. Min Act: -0.0003

Data Index: 888419 (C4 (Web Text))

Max Activating Token Index: 45

Text #17

Max Range: 1.0735. Min Range: -1.0735

Max Act: 0.4813. Min Act: -0.0003

Data Index: 681912 (C4 (Web Text))

Max Activating Token Index: 813

Text #18

Max Range: 1.0735. Min Range: -1.0735

Max Act: 0.4732. Min Act: -0.0003

Data Index: 563342 (C4 (Web Text))

Max Activating Token Index: 510

Text #19

Max Range: 1.0735. Min Range: -1.0735

Max Act: 0.4002. Min Act: -0.0003

Data Index: 374524 (C4 (Web Text))

Max Activating Token Index: 619